Downloads · 30 days
734
29% of all-time downloads
Chatterbox-Multilingual-MLX-fp16
aufklarer/Chatterbox-Multilingual-MLX-fp16
Chatterbox-Multilingual-MLX-fp16 is a text-to-speech model from aufklarer. Use it when you need text read aloud. It is set up for mlx-audio. The card lists the license as mit.
Multilingual Chatterbox (Resemble AI, MIT) converted to MLX in genuine fp16 for Apple-silicon inference. Unlike mlx-community/chatterbox-fp16 (stored as F32, ~2.6 GB), this bundle stores all float tensors as fp16 (~1.…
All-time downloads
2.6K
Public
Parameters
643M
1.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- mlx-audio
- License
- mit
- Model type
- chatterbox
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Jun 23, 2026
- SHA
- 0a062e0f
Base models
Model card
From the Hugging Face model README
aufklarer/Chatterbox-Multilingual-MLX-fp16
Multilingual Chatterbox (Resemble AI,
MIT) converted to MLX in genuine fp16 for Apple-silicon inference. Unlike
mlx-community/chatterbox-fp16 (stored as F32, ~2.6 GB), this bundle stores all
float tensors as fp16 (~1.3 GB) with an identical key layout.
Zero-shot voice cloning from a short reference clip across 23 languages
(incl. Arabic and Hindi). Component prefixes: ve.* (voice encoder), t3.*
(text→speech-token T3), s3gen.* (token→waveform S3Gen).
Note: requires the S3Tokenizer weights from mlx-community/S3TokenizerV2, downloaded automatically at runtime.
Use with mlx-audio
pip install -U mlx-audio
mlx_audio.tts.generate --model aufklarer/Chatterbox-Multilingual-MLX-fp16 --text "[ar] مرحبا" --ref_audio reference.wav
Converted with models/chatterbox/export/convert.py (speech-models).
- Task
- Text-to-Speech
- Library
- mlx-audio
- Type
- chatterbox
- License
- mit
- Languages
- en, ar, hi, de, es, fr
- Created
- Jun 22, 2026
- Updated
- Jun 23, 2026